© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4816
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms related to medical and psychological research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    361
    +0.11
    0.5%
    314
    +0.10
    0.5%
    2
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.11
    0.03
    314
    +0.10
    -0.00
    232
    +0.09
    0.04
    Negative Logits
    AAF
    -0.71
     TAMADRA
    -0.61
     base
    -0.59
     [+
    -0.59
     allowances
    -0.58
    rake
    -0.57
    LESS
    -0.57
     specificity
    -0.55
    cember
    -0.54
    wit
    -0.54
    POSITIVE LOGITS
    naissance
    0.84
    rencies
    0.78
    ics
    0.77
    imaru
    0.77
    iatric
    0.75
    ocrin
    0.75
    ionage
    0.75
    uct
    0.75
    cious
    0.75
    ternity
    0.74
    Activations Density 0.468%

    No Known Activations